gaotang/RM-R1-DeepSeek-Distilled-Qwen-14B
Full fine-tune vs deepseek-ai/DeepSeek-R1-Distill-Qwen-14B. Fine-tune: 100% of the weights changed, across 48 of 48 layers.
Tensors changed: Embeddings 1/1, Attention 336/336, MLP 144/144, Norms 92/97, lm_head 1/1
2 derivatives checked
- mradermacher/RM-R1-DeepSeek-Distilled-Qwen-14B-i1-GGUF: Quantization
- mradermacher/RM-R1-DeepSeek-Distilled-Qwen-14B-GGUF: Quantization
1 other repos hold byte-for-byte identical weight files.